Authors
Mohamed Sebnat, Anass Abdelhamid El Alami, Hamid Garmani, Mohamed Baslam
Published in
Data in brief. Volume 69. Pages 113406. Epub Nov 04, 2026.
Abstract
Public datasets for RAN-level network slicing remain limited. Existing resources either operate above the RAN layer, overlooking scheduler and queueing dynamics, or rely on closed-loop settings where system behavior is tied to controller actions. This work introduces the Tier-2 Full dataset, generated with ns-3 and the 5G-LENA NR module. It comprises 321,300 slice-level observations aggregated over fixed 100 ms windows from 180 simulation runs across a structured scenario grid spanning mobility, channel conditions, traffic patterns, and load evolution. Each observation reports throughput, delay, jitter, and packet loss at a temporal resolution of 100 ms, together with a binary admission-feasibility label derived from fixed, slice-specific Service Level Agreement (SLA) thresholds applied consistently across scenarios. The dataset is accompanied by a full schema specification, SLA threshold documentation, and reproducibility artifacts sufficient to regenerate all simulation outputs.
PMID:
43034871
Bibliographic data and abstract were imported from PubMed on 15 Nov 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 11
- Comments 0